summaryrefslogtreecommitdiffstats
path: root/net/netfilter/nf_queue.c
blob: 9dc1d6e04946f59ea34377a14834bd711c4cd092 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
/*
 * Rusty Russell (C)2000 -- This code is GPL.
 * Patrick McHardy (c) 2006-2012
 */

#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/skbuff.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_ipv6.h>
#include <linux/netfilter_bridge.h>
#include <linux/seq_file.h>
#include <linux/rcupdate.h>
#include <net/protocol.h>
#include <net/netfilter/nf_queue.h>
#include <net/dst.h>

#include "nf_internals.h"

/*
 * Hook for nfnetlink_queue to register its queue handler.
 * We do this so that most of the NFQUEUE code can be modular.
 *
 * Once the queue is registered it must reinject all packets it
 * receives, no matter what.
 */

/* return EBUSY when somebody else is registered, return EEXIST if the
 * same handler is registered, return 0 in case of success. */
void nf_register_queue_handler(struct net *net, const struct nf_queue_handler *qh)
{
	/* should never happen, we only have one queueing backend in kernel */
	WARN_ON(rcu_access_pointer(net->nf.queue_handler));
	rcu_assign_pointer(net->nf.queue_handler, qh);
}
EXPORT_SYMBOL(nf_register_queue_handler);

/* The caller must flush their queue before this */
void nf_unregister_queue_handler(struct net *net)
{
	RCU_INIT_POINTER(net->nf.queue_handler, NULL);
}
EXPORT_SYMBOL(nf_unregister_queue_handler);

static void nf_queue_entry_release_br_nf_refs(struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);

	if (nf_bridge) {
		struct net_device *physdev;

		physdev = nf_bridge_get_physindev(skb);
		if (physdev)
			dev_put(physdev);
		physdev = nf_bridge_get_physoutdev(skb);
		if (physdev)
			dev_put(physdev);
	}
#endif
}

void nf_queue_entry_release_refs(struct nf_queue_entry *entry)
{
	struct nf_hook_state *state = &entry->state;

	/* Release those devices we held, or Alexey will kill me. */
	if (state->in)
		dev_put(state->in);
	if (state->out)
		dev_put(state->out);
	if (state->sk)
		sock_put(state->sk);

	nf_queue_entry_release_br_nf_refs(entry->skb);
}
EXPORT_SYMBOL_GPL(nf_queue_entry_release_refs);

static void nf_queue_entry_get_br_nf_refs(struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);

	if (nf_bridge) {
		struct net_device *physdev;

		physdev = nf_bridge_get_physindev(skb);
		if (physdev)
			dev_hold(physdev);
		physdev = nf_bridge_get_physoutdev(skb);
		if (physdev)
			dev_hold(physdev);
	}
#endif
}

/* Bump dev refs so they don't vanish while packet is out */
void nf_queue_entry_get_refs(struct nf_queue_entry *entry)
{
	struct nf_hook_state *state = &entry->state;

	if (state->in)
		dev_hold(state->in);
	if (state->out)
		dev_hold(state->out);
	if (state->sk)
		sock_hold(state->sk);

	nf_queue_entry_get_br_nf_refs(entry->skb);
}
EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs);

void nf_queue_nf_hook_drop(struct net *net)
{
	const struct nf_queue_handler *qh;

	rcu_read_lock();
	qh = rcu_dereference(net->nf.queue_handler);
	if (qh)
		qh->nf_hook_drop(net);
	rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(nf_queue_nf_hook_drop);

static void nf_ip_saveroute(const struct sk_buff *skb,
			    struct nf_queue_entry *entry)
{
	struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry);

	if (entry->state.hook == NF_INET_LOCAL_OUT) {
		const struct iphdr *iph = ip_hdr(skb);

		rt_info->tos = iph->tos;
		rt_info->daddr = iph->daddr;
		rt_info->saddr = iph->saddr;
		rt_info->mark = skb->mark;
	}
}

static void nf_ip6_saveroute(const struct sk_buff *skb,
			     struct nf_queue_entry *entry)
{
	struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);

	if (entry->state.hook == NF_INET_LOCAL_OUT) {
		const struct ipv6hdr *iph = ipv6_hdr(skb);

		rt_info->daddr = iph->daddr;
		rt_info->saddr = iph->saddr;
		rt_info->mark = skb->mark;
	}
}

static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state,
		      const struct nf_hook_entries *entries,
		      unsigned int index, unsigned int queuenum)
{
	int status = -ENOENT;
	struct nf_queue_entry *entry = NULL;
	const struct nf_queue_handler *qh;
	struct net *net = state->net;
	unsigned int route_key_size;

	/* QUEUE == DROP if no one is waiting, to be safe. */
	qh = rcu_dereference(net->nf.queue_handler);
	if (!qh) {
		status = -ESRCH;
		goto err;
	}

	switch (state->pf) {
	case AF_INET:
		route_key_size = sizeof(struct ip_rt_info);
		break;
	case AF_INET6:
		route_key_size = sizeof(struct ip6_rt_info);
		break;
	default:
		route_key_size = 0;
		break;
	}

	entry = kmalloc(sizeof(*entry) + route_key_size, GFP_ATOMIC);
	if (!entry) {
		status = -ENOMEM;
		goto err;
	}

	*entry = (struct nf_queue_entry) {
		.skb	= skb,
		.state	= *state,
		.hook_index = index,
		.size	= sizeof(*entry) + route_key_size,
	};

	nf_queue_entry_get_refs(entry);
	skb_dst_force(skb);

	switch (entry->state.pf) {
	case AF_INET:
		nf_ip_saveroute(skb, entry);
		break;
	case AF_INET6:
		nf_ip6_saveroute(skb, entry);
		break;
	}

	status = qh->outfn(entry, queuenum);

	if (status < 0) {
		nf_queue_entry_release_refs(entry);
		goto err;
	}

	return 0;

err:
	kfree(entry);
	return status;
}

/* Packets leaving via this function must come back through nf_reinject(). */
int nf_queue(struct sk_buff *skb, struct nf_hook_state *state,
	     const struct nf_hook_entries *entries, unsigned int index,
	     unsigned int verdict)
{
	int ret;

	ret = __nf_queue(skb, state, entries, index, verdict >> NF_VERDICT_QBITS);
	if (ret < 0) {
		if (ret == -ESRCH &&
		    (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS))
			return 1;
		kfree_skb(skb);
	}

	return 0;
}
EXPORT_SYMBOL_GPL(nf_queue);

static unsigned int nf_iterate(struct sk_buff *skb,
			       struct nf_hook_state *state,
			       const struct nf_hook_entries *hooks,
			       unsigned int *index)
{
	const struct nf_hook_entry *hook;
	unsigned int verdict, i = *index;

	while (i < hooks->num_hook_entries) {
		hook = &hooks->hooks[i];
repeat:
		verdict = nf_hook_entry_hookfn(hook, skb, state);
		if (verdict != NF_ACCEPT) {
			if (verdict != NF_REPEAT)
				return verdict;
			goto repeat;
		}
		i++;
	}

	*index = i;
	return NF_ACCEPT;
}

static struct nf_hook_entries *nf_hook_entries_head(const struct net *net, u8 pf, u8 hooknum)
{
	switch (pf) {
#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE
	case NFPROTO_BRIDGE:
		return rcu_dereference(net->nf.hooks_bridge[hooknum]);
#endif
	case NFPROTO_IPV4:
		return rcu_dereference(net->nf.hooks_ipv4[hooknum]);
	case NFPROTO_IPV6:
		return rcu_dereference(net->nf.hooks_ipv6[hooknum]);
	default:
		WARN_ON_ONCE(1);
		return NULL;
	}

	return NULL;
}

/* Caller must hold rcu read-side lock */
void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
{
	const struct nf_hook_entry *hook_entry;
	const struct nf_hook_entries *hooks;
	struct sk_buff *skb = entry->skb;
	const struct net *net;
	unsigned int i;
	int err;
	u8 pf;

	net = entry->state.net;
	pf = entry->state.pf;

	hooks = nf_hook_entries_head(net, pf, entry->state.hook);

	nf_queue_entry_release_refs(entry);

	i = entry->hook_index;
	if (WARN_ON_ONCE(!hooks || i >= hooks->num_hook_entries)) {
		kfree_skb(skb);
		kfree(entry);
		return;
	}

	hook_entry = &hooks->hooks[i];

	/* Continue traversal iff userspace said ok... */
	if (verdict == NF_REPEAT)
		verdict = nf_hook_entry_hookfn(hook_entry, skb, &entry->state);

	if (verdict == NF_ACCEPT) {
		if (nf_reroute(skb, entry) < 0)
			verdict = NF_DROP;
	}

	if (verdict == NF_ACCEPT) {
next_hook:
		++i;
		verdict = nf_iterate(skb, &entry->state, hooks, &i);
	}

	switch (verdict & NF_VERDICT_MASK) {
	case NF_ACCEPT:
	case NF_STOP:
		local_bh_disable();
		entry->state.okfn(entry->state.net, entry->state.sk, skb);
		local_bh_enable();
		break;
	case NF_QUEUE:
		err = nf_queue(skb, &entry->state, hooks, i, verdict);
		if (err == 1)
			goto next_hook;
		break;
	case NF_STOLEN:
		break;
	default:
		kfree_skb(skb);
	}

	kfree(entry);
}
EXPORT_SYMBOL(nf_reinject);